Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5862 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.8063. Min Act: -0.1700
Data Index: 4814930 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.7125. Min Act: -0.1700
Data Index: 8316075 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.6188. Min Act: -0.1700
Data Index: 5025255 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.6500. Min Act: -0.1700
Data Index: 4891004 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5875. Min Act: -0.1700
Data Index: 7571519 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 454668 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5875. Min Act: -0.1700
Data Index: 7495097 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5875. Min Act: -0.1700
Data Index: 7483318 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5875. Min Act: -0.1700
Data Index: 570136 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.6188. Min Act: -0.1700
Data Index: 4848260 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 7403993 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5875. Min Act: -0.1700
Data Index: 8320615 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.6188. Min Act: -0.1700
Data Index: 5532150 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5875. Min Act: -0.1700
Data Index: 5451902 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 8023514 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 4138476 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 1295084 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 334286 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 6610093 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8063. Min Range: -7.8063
Max Act: 7.5563. Min Act: -0.1700
Data Index: 1966010 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19